Writing a script

    # Hello I am starting my R script
    
    goodnumber <- 119
    
    2 * goodnumber

## [1] 238

Functions

    # Combine
    c(3, 4, 5)

## [1] 3 4 5

    # Mean
    mean(c(3, 4, 5))

## [1] 4

    # In steps
    goodnumbers <- c(3, 4, 5)
    mean(goodnumbers)

## [1] 4

    # Looking at some data
    print(mtcars)

##                      mpg cyl  disp  hp drat    wt  qsec vs am gear carb
## Mazda RX4           21.0   6 160.0 110 3.90 2.620 16.46  0  1    4    4
## Mazda RX4 Wag       21.0   6 160.0 110 3.90 2.875 17.02  0  1    4    4
## Datsun 710          22.8   4 108.0  93 3.85 2.320 18.61  1  1    4    1
## Hornet 4 Drive      21.4   6 258.0 110 3.08 3.215 19.44  1  0    3    1
## Hornet Sportabout   18.7   8 360.0 175 3.15 3.440 17.02  0  0    3    2
## Valiant             18.1   6 225.0 105 2.76 3.460 20.22  1  0    3    1
## Duster 360          14.3   8 360.0 245 3.21 3.570 15.84  0  0    3    4
## Merc 240D           24.4   4 146.7  62 3.69 3.190 20.00  1  0    4    2
## Merc 230            22.8   4 140.8  95 3.92 3.150 22.90  1  0    4    2
## Merc 280            19.2   6 167.6 123 3.92 3.440 18.30  1  0    4    4
## Merc 280C           17.8   6 167.6 123 3.92 3.440 18.90  1  0    4    4
## Merc 450SE          16.4   8 275.8 180 3.07 4.070 17.40  0  0    3    3
## Merc 450SL          17.3   8 275.8 180 3.07 3.730 17.60  0  0    3    3
## Merc 450SLC         15.2   8 275.8 180 3.07 3.780 18.00  0  0    3    3
## Cadillac Fleetwood  10.4   8 472.0 205 2.93 5.250 17.98  0  0    3    4
## Lincoln Continental 10.4   8 460.0 215 3.00 5.424 17.82  0  0    3    4
## Chrysler Imperial   14.7   8 440.0 230 3.23 5.345 17.42  0  0    3    4
## Fiat 128            32.4   4  78.7  66 4.08 2.200 19.47  1  1    4    1
## Honda Civic         30.4   4  75.7  52 4.93 1.615 18.52  1  1    4    2
## Toyota Corolla      33.9   4  71.1  65 4.22 1.835 19.90  1  1    4    1
## Toyota Corona       21.5   4 120.1  97 3.70 2.465 20.01  1  0    3    1
## Dodge Challenger    15.5   8 318.0 150 2.76 3.520 16.87  0  0    3    2
## AMC Javelin         15.2   8 304.0 150 3.15 3.435 17.30  0  0    3    2
## Camaro Z28          13.3   8 350.0 245 3.73 3.840 15.41  0  0    3    4
## Pontiac Firebird    19.2   8 400.0 175 3.08 3.845 17.05  0  0    3    2
## Fiat X1-9           27.3   4  79.0  66 4.08 1.935 18.90  1  1    4    1
## Porsche 914-2       26.0   4 120.3  91 4.43 2.140 16.70  0  1    5    2
## Lotus Europa        30.4   4  95.1 113 3.77 1.513 16.90  1  1    5    2
## Ford Pantera L      15.8   8 351.0 264 4.22 3.170 14.50  0  1    5    4
## Ferrari Dino        19.7   6 145.0 175 3.62 2.770 15.50  0  1    5    6
## Maserati Bora       15.0   8 301.0 335 3.54 3.570 14.60  0  1    5    8
## Volvo 142E          21.4   4 121.0 109 4.11 2.780 18.60  1  1    4    2

    # Find out more about functions or data
    ?mtcars
    ?mean
    
    # Look at a single column with $
    print(mtcars$mpg)

##  [1] 21.0 21.0 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 17.8 16.4 17.3 15.2
## [15] 10.4 10.4 14.7 32.4 30.4 33.9 21.5 15.5 15.2 13.3 19.2 27.3 26.0 30.4
## [29] 15.8 19.7 15.0 21.4

    # Get the mean of a single column
    mean(mtcars$mpg)

## [1] 20.09062

Packages

install.packages("tidyverse")

# Load the package
library(tidyverse)

Reading data into R

Tip: when you open quotation marks "", hit TAB to navigate to a file.

gapminder <- read_csv("data/gapminder.csv")

Looking at our data

# Looking at our data
head(gapminder)

## # A tibble: 6 x 6
##   country     continent  year lifeExp      pop gdpPercap
##   <chr>       <chr>     <dbl>   <dbl>    <dbl>     <dbl>
## 1 Afghanistan Asia       1952    28.8  8425333      779.
## 2 Afghanistan Asia       1957    30.3  9240934      821.
## 3 Afghanistan Asia       1962    32.0 10267083      853.
## 4 Afghanistan Asia       1967    34.0 11537966      836.
## 5 Afghanistan Asia       1972    36.1 13079460      740.
## 6 Afghanistan Asia       1977    38.4 14880372      786.

Using ggplot

    # Simple plot
    ggplot(data = gapminder) + 
      aes(x = lifeExp, 
          y = gdpPercap) +
      geom_point()

    # Save your plot
    ggsave("atlas/simple_plot.pdf")

Adding more and assigning to an object, p:

# Adding more and assigning to p
p <- ggplot(data = gapminder) +
  aes(x = lifeExp,
      y = gdpPercap,
      colour = continent,
      size = pop) +
  geom_point(alpha = 0.3) +
  geom_smooth() +
  scale_y_log10() +
  facet_wrap(~continent)

# Plotting p
p

p_facet <- p +
           facet_wrap(~continent)

# Exercise
 ggplot(data = gapminder) +
  aes(x = gdpPercap,
      y = pop,
      colour = lifeExp,
      group = country) +
  geom_point(alpha = 0.8, 
             size = 2) +
  scale_y_log10() +
  scale_x_log10() +
  theme_dark()

Interactive charts with plotly

Install:

install.packages("plotly")

Load:

library(plotly)

Take our p plot and put it inside ggplotly:

ggplotly(p_facet)

Animation

Install required packages.

install.packages("gifski")
install.packages("png")
install.packages("gganimate")

Load gganimate package. The gifski and png packages are background packages used by gganimate and don’t need to be loaded:

library(gganimate)

dancing_gapminder <- ggplot(data = gapminder) +
  aes(x = lifeExp,
      y = gdpPercap,
      colour = continent) +
  geom_point(size = 3) +
  scale_y_log10() +
  facet_wrap(~continent) +
  labs(title = "Year {round(frame_time, 0)}") +
  # This is the animation part:
  transition_time(year)

# View your animation
dancing_gapminder

# Save your animation
anim_save("atlas/dancing_gapminder.gif")

Doing it all together:

gapminder07 <- gapminder %>% 
  mutate(gdp = gdpPercap * pop) %>% 
  filter(year == 2007) %>% 
  select(-gdpPercap)

Exercise

  # Create dataset
  aus <- gapminder %>% 
    filter(country == "Australia") %>% 
    mutate(gdpPClife = gdpPercap / lifeExp)
  
  # Plot
  aus %>% 
    ggplot() +
    aes(gdpPClife,
        pop,
        colour = year) +
    geom_point() +
    geom_line()

Read the sf object

We use the sf package to wrangle mapping data:

install.packages("sf")

Load it:

library(sf)

Read gapminder + geometry data:

gapmap <- read_rds("data/gapmapdata.Rds")

Look at the names of the sf object:

names(gapmap)

## [1] "country"   "continent" "year"      "lifeExp"   "pop"       "gdpPercap"
## [7] "geometry"

Plot an empty map using geom_sf

ggplot(gapmap) +
  aes(geometry = geometry) +
  geom_sf()

Add some data and remove lines between countries

ggplot(gapmap) +
  aes(geometry = geometry,
      fill = gdpPercap) +
  geom_sf(lwd = 0)

# Save map
ggsave("atlas/world_gdp_map.pdf")

Doing more

We can use pipes %>% and filter to look at specific areas (or we can remove areas). For example, we can remove Antarctica:

gapmap %>% 
  filter(country != "Antarctica") %>% 
  ggplot() +
  aes(geometry = geometry,
      fill = gdpPercap) +
  geom_sf(lwd = 0)

Or only include the continent ‘Americas’:

gapmap %>% 
  filter(continent == "Americas") %>% 
  ggplot() +
  aes(geometry = geometry,
      fill = gdpPercap) +
  geom_sf(lwd = 0)

ggsave("atlas/americas_gdp.pdf")

Looking at multiple plots with gridExtra

We can generate multiple plots and present them together using the gridExtra package:

install.packages("gridExtra")

And load it:

library(gridExtra)

Create the first plot and assign to plot1

# Plot 1: americas by gdpPercap
plot1 <- gapmap %>% 
  filter(continent == "Americas") %>% 
  ggplot() +
  aes(geometry = geometry,
      fill = gdpPercap/1000) +  # GDP per capita in thousands
  geom_sf(lwd = 0) +
  coord_sf(datum = NA) +
  theme_void() +
  theme(legend.position = "bottom") +
  labs(subtitle = "GDP per capita (thousands)",
       fill = "")

And the second plot assigned to plot2:

# Plot 2: americas by gdpPercap
plot2 <- gapmap %>% 
  filter(continent == "Americas") %>% 
  ggplot() +
  aes(geometry = geometry,
      fill = lifeExp) +
  geom_sf(lwd = 0) +
  coord_sf(datum = NA) +
  theme_void() +
  theme(legend.position = "bottom") +
  labs(subtitle = "Life expectancy",
       fill = "")

Then use grid.arrange to arrange the plots side-by-side with a title at the top:

    # Arrange the two plots side-by-side: 
    americas_map  <- grid.arrange(plot1, plot2, ncol = 2,
                                  top = "GDP and life expectancy in the Americas, 2007")

    # Save your plot
    ggsave("atlas/americas_map.pdf", plot = americas_map)